* Copyright (c) 2025 Huawei Technologies Co., Ltd.
* This program is free software, you can redistribute it and/or modify it under the terms and conditions of
* CANN Open Software License Agreement Version 2.0 (the "License").
* Please refer to the License for details. You may not use this file except in compliance with the License.
* THIS SOFTWARE IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED,
* INCLUDING BUT NOT LIMITED TO NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE.
* See LICENSE in the root of the software repository for the full text of the License.
*/
* \file kernel_operator_vec_mulcast_intf_impl.h
* \brief
*/
#ifndef ASCENDC_MODULE_OPERATOR_VEC_MULCAST_INTERFACE_IMPL_H
#define ASCENDC_MODULE_OPERATOR_VEC_MULCAST_INTERFACE_IMPL_H
#include "kernel_tensor.h"
#include "kernel_check.h"
#include "kernel_struct_binary.h"
#if __NPU_ARCH__ == 1001
#include "dav_c100/kernel_operator_vec_mulcast_impl.h"
#elif __NPU_ARCH__ == 2002
#include "dav_m200/kernel_operator_vec_mulcast_impl.h"
#elif __NPU_ARCH__ == 2201
#include "dav_c220/kernel_operator_vec_mulcast_impl.h"
#elif __NPU_ARCH__ == 3002
#include "dav_m300/kernel_operator_vec_mulcast_impl.h"
#elif __NPU_ARCH__ == 3102
#include "dav_m310/kernel_operator_vec_mulcast_impl.h"
#elif __NPU_ARCH__ == 3101
#include "dav_c310/kernel_operator_vec_mulcast_impl.h"
#elif (__NPU_ARCH__ == 5102)
#include "dav_m510/kernel_operator_vec_mulcast_impl.h"
#elif (__NPU_ARCH__ == 3003)
#include "dav_l300/kernel_operator_vec_mulcast_impl.h"
#elif (__NPU_ARCH__ == 3113)
#include "dav_l311/kernel_operator_vec_mulcast_impl.h"
#endif
#pragma begin_pipe(V)
namespace AscendC {
template <typename T, typename U, bool isSetMask>
__aicore__ inline void MulCast(const LocalTensor<T> &dst, const LocalTensor<U> &src0,
const LocalTensor<U> &src1, uint64_t mask, const uint8_t repeatTime, const BinaryRepeatParams &repeatParams)
{
using DstPrimType = PrimT<T>;
using SrcPrimType = PrimT<U>;
ASCENDC_ASSERT((SupportType<SrcPrimType, half>() && SupportType<DstPrimType, int8_t, uint8_t>()), {
KERNEL_LOG(KERNEL_ERROR, "Failed "
"to check dtype in MulCast, current api support dtype combination is src: half, dst: int8_t / uint8_t");});
#if ASCENDC_CPU_DEBUG
if (!CheckFuncVecBinaryDiffType(dst, src0, src1, mask, repeatTime, repeatParams, "MulCast")) {
ASCENDC_REPORT_CHECK_ERROR("MulCast", KernelFuncType::MASK_COUNT_MODE);
}
#endif
MulCastCalc<DstPrimType, SrcPrimType, isSetMask>(dst, src0, src1, mask, repeatTime, repeatParams);
}
template <typename T, typename U, bool isSetMask>
__aicore__ inline void MulCast(const LocalTensor<T> &dst, const LocalTensor<U> &src0,
const LocalTensor<U> &src1, uint64_t mask[], const uint8_t repeatTime,
const BinaryRepeatParams &repeatParams)
{
using DstPrimType = PrimT<T>;
using SrcPrimType = PrimT<U>;
ASCENDC_ASSERT((SupportType<SrcPrimType, half>() && SupportType<DstPrimType, int8_t, uint8_t>()), {
KERNEL_LOG(KERNEL_ERROR, "Failed "
"to check dtype in MulCast, current api support dtype combination is src: half, dst: int8_t / uint8_t");});
#if ASCENDC_CPU_DEBUG
if (!CheckFuncVecBinaryDiffType(dst, src0, src1, mask, repeatTime, repeatParams, "MulCast")) {
ASCENDC_REPORT_CHECK_ERROR("MulCast", KernelFuncType::MASK_BIT_MODE);
}
#endif
MulCastCalc<DstPrimType, SrcPrimType, isSetMask>(dst, src0, src1, mask, repeatTime, repeatParams);
}
template <typename T, typename U>
__aicore__ inline void MulCast(const LocalTensor<T> &dst, const LocalTensor<U> &src0,
const LocalTensor<U> &src1, uint32_t count)
{
#if ASCENDC_CPU_DEBUG
if (!CheckFuncVecBinaryDiffType(dst, src0, src1, count, "MulCast")) {
ASCENDC_REPORT_CHECK_ERROR("MulCast", KernelFuncType::CALCOUNT_MODE);
}
#endif
MulCastCalc(dst, src0, src1, count);
}
}
#pragma end_pipe
#endif
